PyPI page
Home page
Author:
Harun Ercul
Summary:
LLM cost routing with correct per-request cost: output-length forecasting, cache-aware tiered pricing, and $/quality ranking.
Latest version:
0.0.0
Required dependencies:
httpx
Optional dependencies:
fastapi
|
numpy
|
scipy
|
typer
|
uvicorn
Downloads last day:
3
Downloads last week:
15
Downloads last month:
108
7-day smoothing